相关论文: Text Augmentation for Language Models in High Erro…

Recent studies have found that model performance has a smooth power-law relationship, or scaling laws, with training data and model size, for a wide range of problems. These scaling laws allow one to choose nearly optimal data and model…

Advances in natural language processing, such as transfer learning from pre-trained language models, have impacted how models are trained for programming language tasks too. Previous research primarily explored code pre-training and…

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that…

For a speech-enhancement algorithm, it is highly desirable to simultaneously improve perceptual quality and recognition rate. Thanks to computational costs and model complexities, it is challenging to train a model that effectively…

Psychoacoustic studies have shown that locally-time reversed (LTR) speech, i.e., signal samples time-reversed within a short segment, can be accurately recognised by human listeners. This study addresses the question of how well a…

This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training data and their…

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strategies to address this problem, there are few studies that…

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

Recent years have seen an increased interest in the computational speech processing of Maltese, but resources remain sparse. In this paper, we consider data augmentation techniques for improving speech recognition for low-resource…

Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one for speaker verification (SV), especially for under-resourced…

Children's automatic speech recognition (ASR) is always difficult due to, in part, the data scarcity problem, especially for kindergarten-aged kids. When data are scarce, the model might overfit to the training data, and hence good starting…

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many challenges, mainly due to data scarcity, grammatical…

Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples equally without considering their individual impacts on the…

Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of sensitivity to word order on controlled challenge sets. We…

Speech Emotion Recognition (SER) is crucial for human-computer interaction but still remains a challenging problem because of two major obstacles: data scarcity and imbalance. Many datasets for SER are substantially imbalanced, where data…

This paper explores the potential of leveraging Large Language Models (LLMs) for data augmentation in multilingual commonsense reasoning datasets where the available training data is extremely limited. To achieve this, we utilise several…

Multilingual end-to-end automatic speech recognition models are attractive due to its simplicity in training and deployment. Recent work on large-scale training of such models has shown promising results compared to monolingual models.…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…